Spies in everyday life: how a vacuum cleaner can eavesdrop on you

[zakiyatasnim]

Can household appliances spy on us? Yes, and scientists from Singapore have discovered one method of hacking a home robot vacuum cleaner. As a result of the experiment, they turned it into a spy robot that can pick up sounds.



Scientists from the National University of Singapore have portugal number data discovered a way to capture sounds in a room using a robot vacuum cleaner. However, the vacuum cleaner that the experts tested does not have a built-in microphone. The principle of eavesdropping is slightly different - instead of a microphone, lidar is used.




Lidar consists of two elements: a laser emitter and a receiver. Lidar measures the distance to objects with high accuracy using a laser beam. And, as it turned out, with the help of a laser you can perfectly hear everything that is happening around the spy robot.



What is the essence of the experiment? The vacuum cleaner was installed next to the garbage can. The lidar was directed at the bucket. An audio speaker was installed 20 cm from the bucket, which reproduced a sound with a volume of about 70 dB. As a result of using specialized equipment, the researchers managed not only to eavesdrop on the sound. As it turned out, this technology allows:

from 96% - to determine the gender of the speaker,
from 91% - to restore the spoken numbers,
with 90% – identify musical screensavers (chosen from 10 possible ones),
with 67.5% – identifying the person speaking in the room (also a sample of 10 possible).

The principle of operation of lidar

How is the recording done? The lidar rotates at a frequency of 5 Hz, recording 360 distance values ​​per revolution. But this recording frequency is not enough. Scientists modified the electrical circuit in the device unit so that it records the distance without rotation. Under such conditions, the recording frequency increases 360 times to 1.8 kHz.

What next? Then the data is filtered. The empty fragments that remain when the beam does not return are recognized. They also reject low-frequency noise and amplify the sound in low frequencies. The resulting signal is processed by neural network algorithms.



The neural network assigns sounds to classes it knows. The engineers trained the neural network on an open source database, Free Spoken Digit, as well as on their own collection of music screensavers from YouTube.

What other ways are there?

Screenshot of the recording with the sound recovery scheme from the chip package

A few years ago, scientists from the Massachusetts Institute of Technology (MIT) demonstrated how sound can be restored in the most unexpected ways. In one case, they restored a melody from a houseplant. In another experiment, they filmed and restored audio that sounds next to a packet of chips. The sound was converted using a high-speed camera: by changing the pixels in the image of the object being filmed.


Lamphone system

This summer, scientists in Israel eavesdropped on a conversation that was going on in a house in real time, using the vibrations of a light bulb. The method was called Lamphone. This requires a telescope with a photodiode connected to it. The optical receiver converts the light falling on it into an electrical signal. Using an algorithm, the signal is translated into a speech spectrogram, from which the dialogue of the interlocutors is extracted.